When you log into your streaming service, have you ever wondered how the service seems to know exactly what you want to watch? Or, conversely, why it suggests shows and movies you wouldn’t have picked on your own? It’s all thanks to machine learning.
Machine learning is training computer models to predict outcomes. This happens through a combination of math, science, and data. And because you’re not telling the machine what the right answer is, you have to teach it how to infer what the right answer is, which takes time, experimentation, and a lot of data.
Machine Learning Overview
Machine learning is the intersection of computer science and data science to build and train artificial intelligence (AI). Using data, algorithms, and statistics, engineers “teach” a computer how to learn.
This training is similar to the way humans learn. When you’re trying to master something new, you make mistakes. But over time, you learn from those mistakes and improve. Machine learning is similar in that, over time, it learns and improves its accuracy.
But unlike a human, the AI isn’t thinking. It can’t necessarily generate new concepts and ideas. What it’s really doing is making classifications and predictions based on the information it already has. Here’s a simple example of how machine learning operates in real life.
Your streaming service has probably offered you suggestions, and these are based on two data points. First, depending on what you’ve watched, the service will make suggestions based on other people’s viewing habits. It usually looks like, “People who watched X have also watched …”
The second data point comes from what you do with that information. Whether or not you watch the show, the service integrates that information into future suggestions and (theoretically) makes better suggestions in the future.
In a sense, you’re acting as a machine learning engineer, teaching and training the service’s AI to help it improve its accuracy for you and other viewers.
>>MORE: What Is a Data Engineer?
How Does Machine Learning Work?
There are three types of machine learning: supervised, unsupervised, and reinforced. Each of these methods helps the AI make better decisions, and they all work in a similar way.
Machine learning starts by training the model. This training is done with data sets. The machine looks at various data sets to analyze and determine what the correct output is.
Let’s go back to the streaming service. How does it decide what the “right” suggestion is for your next binge-fest?
It starts with training. To keep things simple, we’ll consider only movies. The “movie” category is one data set: movies. It’s pretty big, though, so the movies are in genres: horror, rom-coms, thrillers, and so on. Those are other data sets. Then, you’ve got the viewing habits of everyone who uses the movie category. Who watches only rom-coms, who watches only documentaries, and who bounces around genres? This is yet another data set.
To train the service, an engineer feeds all this information to the AI and lets it analyze the data to identify patterns. For example, it may find that most people who watch horror movies never watch rom-coms but do watch thrillers. It could find out that people who watch sci-fi movies almost always switch over to a comedy the next time.
Cognizant Artificial Intelligence
Try your hand at machine learning. Perform exploratory data analysis, set up an algorithm, and review the machine's performance
Avg. Time: 3-4 Hours
Skills you’ll build: Data analysis, machine learning, model interpretation, data modeling, quality assurance
From these patterns, the machine learns and starts predicting that if you watch horror movies, you’re more likely to watch the horror or thriller movie it suggests than the rom-com (unless it includes horror elements!).
Types of Machine Learning
So, that’s how machine learning works. However, just like there are different teaching methods, there are also different training methods, each with the same end goal: train the AI to make correct predictions.
Supervised Machine Learning
In supervised learning, the machine’s algorithms are trained using labeled data sets which makes it easier for the AI to find patterns. So, the streaming service would label which movies are sci-fi, which are foreign languages, and so on. This makes it easier for the AI to understand that a movie with an alien invasion is probably a sci-fi movie.
Unsupervised Machine Learning
Unsupervised learning means the algorithm analyzes unlabeled data sets and discovers the hidden pattern on its own. This can help the AI uncover patterns and trends the engineers may not have realized existed. For example, the AI may find that people who stream at 2:00 a.m. are more likely to stream documentaries than thrillers.
>>MORE: What Is Data Engineering?
Reinforced Machine Learning
This is similar to supervised learning, but there is no training with sample data. Instead, the machine learns from its successes and mistakes (much like a human does). A famous example of reinforced machine learning is the IBM Watson system that won Jeopardy! in 2011.
For our streaming service, an example would be whether or not you watch something the service suggests.
The “Fourth” Type of Machine Learning
Some also say that semi-supervised machine learning is the fourth type. In this training method, the machine uses a small labeled data set as a guide when analyzing larger, unlabeled data sets. Think of it as using a “cheat sheet” to more quickly get through the information.
How Do Companies Use Machine Learning?
But where does all of this lead? Fortunately, it leads to lots of inventions across a variety of fields. Examples include:
- Image analysis: Companies train AI to better analyze images (like being able to tell the difference between a human and a picture).
- Fraud detection: AI learns what your normal spending patterns are and aren’t to quickly identify when your credit card has been compromised.
- Chatbots: Sometimes that online conversation with customer service isn’t with a human!
- Medical diagnostics: AI is being trained to assist doctors with finding medical issues the human doctor might miss.
>>MORE: Wondering if a chatbot can help you find a job? Learn how to use ChatGPT in your job search.
Machine Learning: The Bottom Line
Though machine learning and AI are still relatively new, it’s found its way into much of our lives. Every time you watch a suggested movie, click on a recommended post, or use your credit card, you’re helping train a machine.
Curious about the machine learning field? Learn how to become a machine learning engineer.
Image credit: Canva